InterNet: Detection of Active Abdominal Arterial Bleeding Using Emergency Digital Subtraction Angiography Imaging With Two-Stage Deep Learning
ObjectiveActive abdominal arterial bleeding is an emergency medical condition. Herein, we present our use of this two-stage InterNet model for detection of active abdominal arterial bleeding using emergency DSA imaging.MethodsFirstly, 450 patients who underwent abdominal DSA procedures were randomly...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-06-01
|
Series: | Frontiers in Medicine |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2022.762091/full |
_version_ | 1811332840260894720 |
---|---|
author | Xiangde Min Zhaoyan Feng Junfeng Gao Shu Chen Peipei Zhang Tianyu Fu Hong Shen Nan Wang |
author_facet | Xiangde Min Zhaoyan Feng Junfeng Gao Shu Chen Peipei Zhang Tianyu Fu Hong Shen Nan Wang |
author_sort | Xiangde Min |
collection | DOAJ |
description | ObjectiveActive abdominal arterial bleeding is an emergency medical condition. Herein, we present our use of this two-stage InterNet model for detection of active abdominal arterial bleeding using emergency DSA imaging.MethodsFirstly, 450 patients who underwent abdominal DSA procedures were randomly selected for development of the region localization stage (RLS). Secondly, 160 consecutive patients with active abdominal arterial bleeding were included for development of the bleeding site detection stage (BSDS) and InterNet (cascade network of RLS and BSDS). Another 50 patients that ruled out active abdominal arterial bleeding were used as negative samples to evaluate InterNet performance. We evaluated the mode's efficacy using the precision-recall (PR) curve. The classification performance of a doctor with and without InterNet was evaluated using a receiver operating characteristic (ROC) curve analysis.ResultsThe AP, precision, and recall of the RLS were 0.99, 0.95, and 0.99 in the validation dataset, respectively. Our InterNet reached a recall of 0.7, the precision for detection of bleeding sites was 53% in the evaluation set. The AUCs of doctors with and without InterNet were 0.803 and 0.759, respectively. In addition, the doctor with InterNet assistant could significantly reduce the elapsed time for the interpretation of each DSA sequence from 84.88 to 43.78 s.ConclusionOur InterNet system could assist interventional radiologists in identifying bleeding foci quickly and may improve the workflow of the DSA operation to a more real-time procedure. |
first_indexed | 2024-04-13T16:43:07Z |
format | Article |
id | doaj.art-ada1787baa374813a51d38e4fb8549cd |
institution | Directory Open Access Journal |
issn | 2296-858X |
language | English |
last_indexed | 2024-04-13T16:43:07Z |
publishDate | 2022-06-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Medicine |
spelling | doaj.art-ada1787baa374813a51d38e4fb8549cd2022-12-22T02:39:10ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2022-06-01910.3389/fmed.2022.762091762091InterNet: Detection of Active Abdominal Arterial Bleeding Using Emergency Digital Subtraction Angiography Imaging With Two-Stage Deep LearningXiangde Min0Zhaoyan Feng1Junfeng Gao2Shu Chen3Peipei Zhang4Tianyu Fu5Hong Shen6Nan Wang7Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaDepartment of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaCollege of Biomedical Engineering, South-Central of University for Nationalities, Wuhan, ChinaUnited Imaging Intelligence, Shanghai, ChinaDepartment of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaUnited Imaging Intelligence, Shanghai, ChinaUnited Imaging Intelligence, Shanghai, ChinaDepartment of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaObjectiveActive abdominal arterial bleeding is an emergency medical condition. Herein, we present our use of this two-stage InterNet model for detection of active abdominal arterial bleeding using emergency DSA imaging.MethodsFirstly, 450 patients who underwent abdominal DSA procedures were randomly selected for development of the region localization stage (RLS). Secondly, 160 consecutive patients with active abdominal arterial bleeding were included for development of the bleeding site detection stage (BSDS) and InterNet (cascade network of RLS and BSDS). Another 50 patients that ruled out active abdominal arterial bleeding were used as negative samples to evaluate InterNet performance. We evaluated the mode's efficacy using the precision-recall (PR) curve. The classification performance of a doctor with and without InterNet was evaluated using a receiver operating characteristic (ROC) curve analysis.ResultsThe AP, precision, and recall of the RLS were 0.99, 0.95, and 0.99 in the validation dataset, respectively. Our InterNet reached a recall of 0.7, the precision for detection of bleeding sites was 53% in the evaluation set. The AUCs of doctors with and without InterNet were 0.803 and 0.759, respectively. In addition, the doctor with InterNet assistant could significantly reduce the elapsed time for the interpretation of each DSA sequence from 84.88 to 43.78 s.ConclusionOur InterNet system could assist interventional radiologists in identifying bleeding foci quickly and may improve the workflow of the DSA operation to a more real-time procedure.https://www.frontiersin.org/articles/10.3389/fmed.2022.762091/fullabdominal arterial bleedingdigital subtraction angiographydeep learningautomatic detectiontwo-stage model |
spellingShingle | Xiangde Min Zhaoyan Feng Junfeng Gao Shu Chen Peipei Zhang Tianyu Fu Hong Shen Nan Wang InterNet: Detection of Active Abdominal Arterial Bleeding Using Emergency Digital Subtraction Angiography Imaging With Two-Stage Deep Learning Frontiers in Medicine abdominal arterial bleeding digital subtraction angiography deep learning automatic detection two-stage model |
title | InterNet: Detection of Active Abdominal Arterial Bleeding Using Emergency Digital Subtraction Angiography Imaging With Two-Stage Deep Learning |
title_full | InterNet: Detection of Active Abdominal Arterial Bleeding Using Emergency Digital Subtraction Angiography Imaging With Two-Stage Deep Learning |
title_fullStr | InterNet: Detection of Active Abdominal Arterial Bleeding Using Emergency Digital Subtraction Angiography Imaging With Two-Stage Deep Learning |
title_full_unstemmed | InterNet: Detection of Active Abdominal Arterial Bleeding Using Emergency Digital Subtraction Angiography Imaging With Two-Stage Deep Learning |
title_short | InterNet: Detection of Active Abdominal Arterial Bleeding Using Emergency Digital Subtraction Angiography Imaging With Two-Stage Deep Learning |
title_sort | internet detection of active abdominal arterial bleeding using emergency digital subtraction angiography imaging with two stage deep learning |
topic | abdominal arterial bleeding digital subtraction angiography deep learning automatic detection two-stage model |
url | https://www.frontiersin.org/articles/10.3389/fmed.2022.762091/full |
work_keys_str_mv | AT xiangdemin internetdetectionofactiveabdominalarterialbleedingusingemergencydigitalsubtractionangiographyimagingwithtwostagedeeplearning AT zhaoyanfeng internetdetectionofactiveabdominalarterialbleedingusingemergencydigitalsubtractionangiographyimagingwithtwostagedeeplearning AT junfenggao internetdetectionofactiveabdominalarterialbleedingusingemergencydigitalsubtractionangiographyimagingwithtwostagedeeplearning AT shuchen internetdetectionofactiveabdominalarterialbleedingusingemergencydigitalsubtractionangiographyimagingwithtwostagedeeplearning AT peipeizhang internetdetectionofactiveabdominalarterialbleedingusingemergencydigitalsubtractionangiographyimagingwithtwostagedeeplearning AT tianyufu internetdetectionofactiveabdominalarterialbleedingusingemergencydigitalsubtractionangiographyimagingwithtwostagedeeplearning AT hongshen internetdetectionofactiveabdominalarterialbleedingusingemergencydigitalsubtractionangiographyimagingwithtwostagedeeplearning AT nanwang internetdetectionofactiveabdominalarterialbleedingusingemergencydigitalsubtractionangiographyimagingwithtwostagedeeplearning |